I basically disagree with the recommendation almost always, including for AI alignment. I do think that
The problem [...] is that it leads people to optimize for absorbing information, rather than seeking it instrumentally, as a precursor to understanding.
I often see the sentiment, “I’m going to learn linear algebra, probability theory, computational complexity, machine learning and deep RL, and then I’ll have the prerequisites to do AI safety”. (Possible reasons for this: the 80K AI safety syllabus, CHAI’s bibliography, a general sense that you have to be an expert before you can do research.) This sentiment seems wrong to me; you definitely can and should think about important questions before learning everything that could potentially be considered “background”.
The advice
let the questions themselves determine how often you need to go back and read papers or study proofs.
sounds to me like “when you feel like existing research would be useful, then go ahead and look at it, but don’t feel like it’s necessary”, whereas I would say “as soon as you have questions, which should be almost immediately, one of the first things you should do is find the existing research and read it”. The justification for this is the standard one—people have already done a bunch of work that you can take advantage of.
The main disadvantage of this approach is that you lose the opportunity to figure things out from first principles. When you figure things out from first principles, you often find many branches that don’t work out, which helps build intuitions about why things are the way they are, which you don’t get nearly as well by reading about research, and you can’t go back and figure things out from first principles because you already know the answer. But this first-principles-reasoning is extremely expensive (in time), and is almost never worthwhile.
Another potential disadvantage is that you might be incorrectly convinced that a technique is good, because you don’t spot the flaws in it when reading existing research, even though you could have figured it out from first principles. My preferred solution is to become good at noticing flaws (e.g. by learning how to identify and question all of the assumptions in an argument), rather than to ignore research entirely.
Side note: In the case of philosophy, if you’re trying to get a paper, then I’m told you often want to make some novel argument (since that’s what gets published), which makes existing research less useful (or only useful to figure out what not to think about). If you want to figure out the truth, I expect you would do well to read existing research.
TL;DR: Looking at existing research is great because you don’t have to reinvent the wheel, but make sure you need the wheel in the first place before you read about it (i.e. make sure you have a question you are reading existing research to answer).
ETA: If your goal is “maximize understanding of X”, then you should never look at existing research about X, and figure everything out from first principles. I’m assuming that you have some reason for caring about X that means you are willing to trade off some understanding for getting it done way faster.
I often see the sentiment, “I’m going to learn linear algebra, probability theory, computational complexity, machine learning and deep RL, and then I’ll have the prerequisites to do AI safety”. (Possible reasons for this: the 80K AI safety syllabus, CHAI’s bibliography, a general sense that you have to be an expert before you can do research.) This sentiment seems wrong to me
I often see the sentiment, “I’m going to learn linear algebra, probability theory, computational complexity, machine learning and deep RL, and then I’ll have the prerequisites to do AI safety”.
Yeah, that feels like a natural extension of “I’m not allowed to have thoughts on this yet, so let me get enough social markers to be allowed to think for myself.” Or ”...to be allowed a thinking license.”
I basically disagree with the recommendation almost always, including for AI alignment. I do think that
I often see the sentiment, “I’m going to learn linear algebra, probability theory, computational complexity, machine learning and deep RL, and then I’ll have the prerequisites to do AI safety”. (Possible reasons for this: the 80K AI safety syllabus, CHAI’s bibliography, a general sense that you have to be an expert before you can do research.) This sentiment seems wrong to me; you definitely can and should think about important questions before learning everything that could potentially be considered “background”.
The advice
sounds to me like “when you feel like existing research would be useful, then go ahead and look at it, but don’t feel like it’s necessary”, whereas I would say “as soon as you have questions, which should be almost immediately, one of the first things you should do is find the existing research and read it”. The justification for this is the standard one—people have already done a bunch of work that you can take advantage of.
The main disadvantage of this approach is that you lose the opportunity to figure things out from first principles. When you figure things out from first principles, you often find many branches that don’t work out, which helps build intuitions about why things are the way they are, which you don’t get nearly as well by reading about research, and you can’t go back and figure things out from first principles because you already know the answer. But this first-principles-reasoning is extremely expensive (in time), and is almost never worthwhile.
Another potential disadvantage is that you might be incorrectly convinced that a technique is good, because you don’t spot the flaws in it when reading existing research, even though you could have figured it out from first principles. My preferred solution is to become good at noticing flaws (e.g. by learning how to identify and question all of the assumptions in an argument), rather than to ignore research entirely.
Side note: In the case of philosophy, if you’re trying to get a paper, then I’m told you often want to make some novel argument (since that’s what gets published), which makes existing research less useful (or only useful to figure out what not to think about). If you want to figure out the truth, I expect you would do well to read existing research.
TL;DR: Looking at existing research is great because you don’t have to reinvent the wheel, but make sure you need the wheel in the first place before you read about it (i.e. make sure you have a question you are reading existing research to answer).
ETA: If your goal is “maximize understanding of X”, then you should never look at existing research about X, and figure everything out from first principles. I’m assuming that you have some reason for caring about X that means you are willing to trade off some understanding for getting it done way faster.
See also, my shortform post about this.
+1, I agree with the “be lazy in the CS sense” prescription; that’s basically what I’m recommending here.
Yeah, that feels like a natural extension of “I’m not allowed to have thoughts on this yet, so let me get enough social markers to be allowed to think for myself.” Or ”...to be allowed a thinking license.”